​
Research Highlights
DARPA Semantic Forensics (SemaFor)
Developed algorithms and systems that automatically detect, attribute, and characterize manipulated and AI generated media.
More resources:
DARPA Explainable AI (XAI)
Developed new machine learning processes, explainable models, and explanation interfaces to help users understand, manage, and appropriately trust AI.
More resources:
DARPA Machine Common Sense (MCS)
Created machine common sense capabilities to enable AI applications to understand new situations, monitor the reasonableness of their actions, communicate more effectively with people, and transfer learning to new domains
More resources:
DARPA In the Moment (ITM)
Quantify the alignment of algorithmic decision-makers with trusted humans in difficult domains where there is no right answer. Enable human-off-the-loop delegation to tactical algorithmic decision-makers for difficult DoD domains.
More resources:
Wide Area Motion Imagery (WAMI) tracking
Took a research capability from concept to operational use in 14 months by leading the design, development, and deployment of a full-frame, real-time, distributed multi-target tracking system. Scaled the technical capability over 70x from a small area of interest to full frame.
